Towards Enriched Controllability for Educational Question Generation
This work addresses the need for more precise control in generating educational questions from children-friendly stories, but it appears incremental as it builds on existing controllability methods.
The study tackled the problem of enriching controllability in educational question generation by introducing a new guidance attribute called question explicitness, and showed preliminary evidence of controlling question generation via this attribute alone and in combination with narrative elements.
Question Generation (QG) is a task within Natural Language Processing (NLP) that involves automatically generating questions given an input, typically composed of a text and a target answer. Recent work on QG aims to control the type of generated questions so that they meet educational needs. A remarkable example of controllability in educational QG is the generation of questions underlying certain narrative elements, e.g., causal relationship, outcome resolution, or prediction. This study aims to enrich controllability in QG by introducing a new guidance attribute: question explicitness. We propose to control the generation of explicit and implicit wh-questions from children-friendly stories. We show preliminary evidence of controlling QG via question explicitness alone and simultaneously with another target attribute: the question's narrative element. The code is publicly available at github.com/bernardoleite/question-generation-control.